Committee-based models (ensembles or cascades) construct models by combining existing pre-trained ones.
Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighbourhoods - that are then trained independently.
Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run.
The sky is a major component of the appearance of a photograph, and its color and tone can strongly influence the mood of a picture.
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory.
Ranking is a central task in machine learning and information retrieval.
The maximization of many of these metrics can be expressed as a constrained optimization problem, where the constraint is a function of the classifier's predictions.
We present MorphNet, an approach to automate the design of neural network structures.
We demonstrate the effectiveness of our approach on several domains and show that, despite the relative simplicity of the structure, prediction accuracy is competitive with a fully connected model that is computationally costly at prediction time.